diff --git a/router/router.py b/router/router.py index 3a02642..2423133 100644 --- a/router/router.py +++ b/router/router.py @@ -233,9 +233,9 @@ def route(rd, tier): result = select_best_gpu(candidates, "medium") if result: return result - # TIER 4: Heavy reasoning — large context or very long conversations → MoE first + # TIER 4: Heavy reasoning — Dense first (thermal), MoE fallback (192K/262K context) if t > 25000 or turns > 15: - candidates = [m for m in ["qwen3.6-35B-A3B","qwen3.6-27B-code","qwen3.5-9b-vlm"] if m in avail] + candidates = [m for m in ["qwen3.6-27B-code","qwen3.6-35B-A3B","qwen3.5-9b-vlm"] if m in avail] result = select_best_gpu(candidates, "heavy_reasoning") if result: return result